triage

A procedure for sorting and classifying GitHub issues by component, priority, size, and milestone.

In plain words
What is it for?
Use it to inspect an issue’s type and parent, find its project item, and set project fields such as priority, size, component, or milestone.
Why use it?
It removes the need to remember GitHub’s project identifiers and API steps when organizing issue work.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/oxidian/cc-plugins/triage
Any agent
npx skills add oxidian/cc-plugins --skill triage
Clone the repo
git clone --depth 1 https://github.com/oxidian/cc-plugins

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 600 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00600
Opus 5 $0.00010 $0.00300
Sonnet 5 $0.00004 $0.00120
Haiku 4.5 $0.00002 $0.00060

Measured 2d ago against content hash e305ff32cf7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

codex/plugins/oxgh/skills/triage/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

First, run these commands and review their output:

  • Current repo: gh repo view --json nameWithOwner --jq '.nameWithOwner'

Getting the item ID

To set project fields, you need the project item ID (not the issue number):

gh project item-list {project_number} --owner {owner} --limit 300 --format json | jq '.items[] | select(.content.number == ISSUE_NUMBER) | .id'

Setting a project field

gh project item-edit --id {item-id} --project-id {project-id} --field-id {field-id} --single-select-option-id {option-id}

Issue types

Check if an issue type is set:

gh api repos/{owner}/{repo}/issues/{number} --jq '.type.name // empty'

Set an issue type (only if not already set):

gh api -X PATCH repos/{owner}/{repo}/issues/{number} --field type=Bug

Valid types: Bug, Feature, Task

Parent issues

Find an issue's parent (for sub-issues):

gh api graphql -f query='
{
  repository(owner: "{owner}", name: "{repo}") {
    issue(number: ISSUE_NUMBER) {
      parent {
        number
        title
      }
    }
  }
}'

Get the parent's project fields (to copy them):

gh project item-list {project_number} --owner {owner} --limit 300 --format json | jq '.items[] | select(.content.number == PARENT_NUMBER)'

Milestones

Check current milestone:

gh api repos/{owner}/{repo}/issues/{number} --jq '.milestone.title // empty'

Set a milestone (use the milestone number, not title):

gh api -X PATCH repos/{owner}/{repo}/issues/{number} --field milestone={milestone-number}

Your task

Based on the user's request:

  1. View the issue to understand its scope: gh api repos/{owner}/{repo}/issues/{number} --jq '{title, body, type: .type.name}'
  2. Get the project item ID for the issue
  3. Determine appropriate Component, Priority, Size, and Type (if not set) based on the issue content
  4. Set all project fields using gh project item-edit
  5. If the issue type is not set, set it using gh api -X PATCH
  6. If the user specified a milestone in their request, set it using gh api -X PATCH
  7. Execute each step as a separate command. Do NOT chain commands with && or ;.

Read the full file on GitHub · 91 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 91 lines · 19 tokens per session scan A e305ff32cf7a

Subscribe to this mod's changes

triage is a skill published in the GitHub repository oxidian/cc-plugins (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 600 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.